Objectives: This research aims to determine the important features including symptoms and risk factors for dengue diagnosis. Methods: The dataset for this study is in the form of medical records collected from two hospitals in East Nusa Tenggara Province including Kewapante and Soe hospitals. Feature selection methods including feature importance, recursive feature elimination, correlation matrix from Pearson correlation coefficient and KBest were leveraged to determine important features. Important features were also gathered from fifteen Indonesian medical doctors to confirm the results. To obtain the best significant features for dengue prediction, we used six machine learning techniques including logistic regression, k-nearest neighbors, eXtreme gradient boosting, random forests, Naive Bayes and support vector machines. Results. The random forest classifier yields the highest accuracy for the best combination of features with the accuracy of 0.93 (LR: 0.90 (0.04), KNN: 0.89 (0.04), XGBoost: 0.91 (0.03), RF: 0.93 (0.04), NB: 0.88 (0.09), SVM: 0.89 (0.04)) and precision of 0.90 (LR: 0.86 (0.22), KNN: 0.67 (0.14), XGBoost: 0.77 (0.13), RF: 0.90 (0.13), NB: 0.66 (0.20), SVM: 0.66 (0.18)). This study shows the significant features for dengue diagnosis including fever, fever duration, headache, muscle and joint pain, nausea, vomiting, abdominal pain, shivering, malaise, loss of appetite, shortness of breath, rash, bleeding nose, bitter mouth, temperature and age. Conclusions. This beneficial information can help society in differentiating dengue from non-dengue diseases including malaria, typhoid fever, COVID-19 and other dengue-like symptoms diseases. This is pivotal to educate society to seek medical advice when dengue symptoms appear. Keywords: Dengue fever, Feature selection, Significant dengue features, Dengue prediction, Dengue diagnosis